// RUN โ€” FITS

Can the AMD Instinct MI300X 192GB run RNA-FrameFlow?

Yes โ€” here's how fast and up to what context, with real measured numbers.

RNA-FrameFlow on the AMD Instinct MI300X 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2672k 99375-121458.3 t/s ~750-916.7 (slow)
Q8 yes 2672k 198750-242916.7 t/s ~1500-1833.3 (slow)
Q4 yes 2672k 354910.7-433779.8 t/s ~2678.6-3273.8 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the AMD Instinct MI300X 192GB run RNA-FrameFlow?โ–ถ

Yes. At Q4 it generates ~354910.7-433779.8 tok/s and fits up to 2672k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2678.6-3273.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2672k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.